600f4bbd55
Preparation for #914 and #920 Changes formatting to ruff and black. Remove python 3.8 ## Additional Changes - Removed flake8 dependencies - Adjusted pre-commit. Now CI and Make use pre-commit, reducing the duplication of linting calls - Removed check-docstyle option (ruff is doing that) - Merged format and lint. In CI the format-lint step fails if any changes are done, so it fulfills the lint functionality. --------- Co-authored-by: Jiayi Weng <jiayi@openai.com>
200 lines
7.0 KiB
Python
200 lines
7.0 KiB
Python
import argparse
|
|
import os
|
|
import pprint
|
|
|
|
import gymnasium as gym
|
|
import numpy as np
|
|
import torch
|
|
from torch.utils.tensorboard import SummaryWriter
|
|
|
|
from tianshou.data import Collector, PrioritizedVectorReplayBuffer, VectorReplayBuffer
|
|
from tianshou.env import DummyVectorEnv
|
|
from tianshou.policy import DQNPolicy, ICMPolicy
|
|
from tianshou.trainer import OffpolicyTrainer
|
|
from tianshou.utils import TensorboardLogger
|
|
from tianshou.utils.net.common import MLP, Net
|
|
from tianshou.utils.net.discrete import IntrinsicCuriosityModule
|
|
|
|
|
|
def get_args():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--task", type=str, default="CartPole-v0")
|
|
parser.add_argument("--reward-threshold", type=float, default=None)
|
|
parser.add_argument("--seed", type=int, default=1626)
|
|
parser.add_argument("--eps-test", type=float, default=0.05)
|
|
parser.add_argument("--eps-train", type=float, default=0.1)
|
|
parser.add_argument("--buffer-size", type=int, default=20000)
|
|
parser.add_argument("--lr", type=float, default=1e-3)
|
|
parser.add_argument("--gamma", type=float, default=0.9)
|
|
parser.add_argument("--n-step", type=int, default=3)
|
|
parser.add_argument("--target-update-freq", type=int, default=320)
|
|
parser.add_argument("--epoch", type=int, default=20)
|
|
parser.add_argument("--step-per-epoch", type=int, default=10000)
|
|
parser.add_argument("--step-per-collect", type=int, default=10)
|
|
parser.add_argument("--update-per-step", type=float, default=0.1)
|
|
parser.add_argument("--batch-size", type=int, default=64)
|
|
parser.add_argument("--hidden-sizes", type=int, nargs="*", default=[128, 128, 128, 128])
|
|
parser.add_argument("--training-num", type=int, default=10)
|
|
parser.add_argument("--test-num", type=int, default=100)
|
|
parser.add_argument("--logdir", type=str, default="log")
|
|
parser.add_argument("--render", type=float, default=0.0)
|
|
parser.add_argument("--prioritized-replay", action="store_true", default=False)
|
|
parser.add_argument("--alpha", type=float, default=0.6)
|
|
parser.add_argument("--beta", type=float, default=0.4)
|
|
parser.add_argument(
|
|
"--device",
|
|
type=str,
|
|
default="cuda" if torch.cuda.is_available() else "cpu",
|
|
)
|
|
parser.add_argument(
|
|
"--lr-scale",
|
|
type=float,
|
|
default=1.0,
|
|
help="use intrinsic curiosity module with this lr scale",
|
|
)
|
|
parser.add_argument(
|
|
"--reward-scale",
|
|
type=float,
|
|
default=0.01,
|
|
help="scaling factor for intrinsic curiosity reward",
|
|
)
|
|
parser.add_argument(
|
|
"--forward-loss-weight",
|
|
type=float,
|
|
default=0.2,
|
|
help="weight for the forward model loss in ICM",
|
|
)
|
|
return parser.parse_known_args()[0]
|
|
|
|
|
|
def test_dqn_icm(args=get_args()):
|
|
env = gym.make(args.task)
|
|
args.state_shape = env.observation_space.shape or env.observation_space.n
|
|
args.action_shape = env.action_space.shape or env.action_space.n
|
|
if args.reward_threshold is None:
|
|
default_reward_threshold = {"CartPole-v0": 195}
|
|
args.reward_threshold = default_reward_threshold.get(args.task, env.spec.reward_threshold)
|
|
# train_envs = gym.make(args.task)
|
|
# you can also use tianshou.env.SubprocVectorEnv
|
|
train_envs = DummyVectorEnv([lambda: gym.make(args.task) for _ in range(args.training_num)])
|
|
# test_envs = gym.make(args.task)
|
|
test_envs = DummyVectorEnv([lambda: gym.make(args.task) for _ in range(args.test_num)])
|
|
# seed
|
|
np.random.seed(args.seed)
|
|
torch.manual_seed(args.seed)
|
|
train_envs.seed(args.seed)
|
|
test_envs.seed(args.seed)
|
|
# Q_param = V_param = {"hidden_sizes": [128]}
|
|
# model
|
|
net = Net(
|
|
args.state_shape,
|
|
args.action_shape,
|
|
hidden_sizes=args.hidden_sizes,
|
|
device=args.device,
|
|
# dueling=(Q_param, V_param),
|
|
).to(args.device)
|
|
optim = torch.optim.Adam(net.parameters(), lr=args.lr)
|
|
policy = DQNPolicy(
|
|
net,
|
|
optim,
|
|
args.gamma,
|
|
args.n_step,
|
|
target_update_freq=args.target_update_freq,
|
|
)
|
|
feature_dim = args.hidden_sizes[-1]
|
|
feature_net = MLP(
|
|
np.prod(args.state_shape),
|
|
output_dim=feature_dim,
|
|
hidden_sizes=args.hidden_sizes[:-1],
|
|
device=args.device,
|
|
)
|
|
action_dim = np.prod(args.action_shape)
|
|
icm_net = IntrinsicCuriosityModule(
|
|
feature_net,
|
|
feature_dim,
|
|
action_dim,
|
|
hidden_sizes=args.hidden_sizes[-1:],
|
|
device=args.device,
|
|
).to(args.device)
|
|
icm_optim = torch.optim.Adam(icm_net.parameters(), lr=args.lr)
|
|
policy = ICMPolicy(
|
|
policy,
|
|
icm_net,
|
|
icm_optim,
|
|
args.lr_scale,
|
|
args.reward_scale,
|
|
args.forward_loss_weight,
|
|
)
|
|
# buffer
|
|
if args.prioritized_replay:
|
|
buf = PrioritizedVectorReplayBuffer(
|
|
args.buffer_size,
|
|
buffer_num=len(train_envs),
|
|
alpha=args.alpha,
|
|
beta=args.beta,
|
|
)
|
|
else:
|
|
buf = VectorReplayBuffer(args.buffer_size, buffer_num=len(train_envs))
|
|
# collector
|
|
train_collector = Collector(policy, train_envs, buf, exploration_noise=True)
|
|
test_collector = Collector(policy, test_envs, exploration_noise=True)
|
|
# policy.set_eps(1)
|
|
train_collector.collect(n_step=args.batch_size * args.training_num)
|
|
# log
|
|
log_path = os.path.join(args.logdir, args.task, "dqn_icm")
|
|
writer = SummaryWriter(log_path)
|
|
logger = TensorboardLogger(writer)
|
|
|
|
def save_best_fn(policy):
|
|
torch.save(policy.state_dict(), os.path.join(log_path, "policy.pth"))
|
|
|
|
def stop_fn(mean_rewards):
|
|
return mean_rewards >= args.reward_threshold
|
|
|
|
def train_fn(epoch, env_step):
|
|
# eps annnealing, just a demo
|
|
if env_step <= 10000:
|
|
policy.set_eps(args.eps_train)
|
|
elif env_step <= 50000:
|
|
eps = args.eps_train - (env_step - 10000) / 40000 * (0.9 * args.eps_train)
|
|
policy.set_eps(eps)
|
|
else:
|
|
policy.set_eps(0.1 * args.eps_train)
|
|
|
|
def test_fn(epoch, env_step):
|
|
policy.set_eps(args.eps_test)
|
|
|
|
# trainer
|
|
result = OffpolicyTrainer(
|
|
policy=policy,
|
|
train_collector=train_collector,
|
|
test_collector=test_collector,
|
|
max_epoch=args.epoch,
|
|
step_per_epoch=args.step_per_epoch,
|
|
step_per_collect=args.step_per_collect,
|
|
episode_per_test=args.test_num,
|
|
batch_size=args.batch_size,
|
|
update_per_step=args.update_per_step,
|
|
train_fn=train_fn,
|
|
test_fn=test_fn,
|
|
stop_fn=stop_fn,
|
|
save_best_fn=save_best_fn,
|
|
logger=logger,
|
|
).run()
|
|
assert stop_fn(result["best_reward"])
|
|
|
|
if __name__ == "__main__":
|
|
pprint.pprint(result)
|
|
# Let's watch its performance!
|
|
env = gym.make(args.task)
|
|
policy.eval()
|
|
policy.set_eps(args.eps_test)
|
|
collector = Collector(policy, env)
|
|
result = collector.collect(n_episode=1, render=args.render)
|
|
rews, lens = result["rews"], result["lens"]
|
|
print(f"Final reward: {rews.mean()}, length: {lens.mean()}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
test_dqn_icm(get_args())
|